Demultiplexing Deepstream output

• Hardware Platform (Jetson / GPU) : Triton Inference server
• DeepStream Version : 5.1

We are using Video analytics on multiple cameras on deepstream. for output we have a requirement of individual camera output for which we are using demultiplexer. however to view one camera output we need one node port on kubernetes GPU.

We have a limitation on the number of nodeports available. Can you tell me a alternative solution for this challenge

where to output?

is it a SW component, or a DeepStream plugin?

what’s nodeports ?

Output to be seen as Livestreaming on a web portal

Demultiplexer is a deepstream component

Nodeport is a port in Kubernetes on GPU setup which is used to expose the rtsp output obtained from Deepstream

Sorry! We are not familar with Kubernetes , if Nodeport is a port in Kubernetes on GPU setup, why can’t increase the port number? What do you expect DS to do for you?

I want a way out in which possibly i could resuse the same nodeports for different cameras based on user request for live streaming. We have a limitations on the number of Nodeport availability in kubernetes, so we cannot increase the number of nodeports